Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    winning competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -sale
    -0.07
     loan
    -0.07
    (Core
    -0.06
    endar
    -0.06
    -sum
    -0.06
     shareholders
    -0.06
     competitors
    -0.06
    gz
    -0.06
     auch
    -0.06
    _bed
    -0.06
    POSITIVE LOGITS
     beloved
    0.07
     resolves
    0.07
    izabeth
    0.07
    awaii
    0.06
     Coco
    0.06
    lags
    0.06
    �
    0.06
     fkk
    0.06
     тем
    0.06
    winner
    0.06
    Act Density 0.039%

    No Known Activations